Description: For establishing the ongoing adequacy of claim reserves for blocks of long-term care insurance, retro testing is a blunt tool, the results of which are not conclusive. Claim reserve retro tests should be reviewed by claim duration, include the impact of interest consistently, and include updated assumptions that can have an impact on claim termination rates or other factors. The new NAIC LTC Experience Reporting Forms estimated to arrive for reporting year 2008 will help modernize LTCI retro tests, providing additional accuracy and standardization. Actuaries should not wait for these forms, but rather ensure that any claim reserve analysis moves beyond a basic calendar year retro test.

Description: Feature article about: one of the significant contributions of modern academic finance has been to introduce the concept of stochastic investment forecasting

Description: This article walks through the process of building a cluster model using off-the-shelf software.

Description: A preview on the Spring Society of Actuaries meetings in May of 2009.

Description: A listing of the 2016 modeling-related sessions and webcasts from the SOA. Most meeting session recordings are available for free to SOA members.

Description: Presented at June 1996 Spring Meeting. This session provides up-to-date information on the redesign effort and the governing principles that guide the design process.

Description: Following up on recent articles on claim reserves and retrospective testing, this article examines some data quality and methodology issues related to calculating LTCI claim reserves.

Description: This article discusses the mechanics of a prospective approach to calculating LTC rate increases and compares it to approaches defined by previous model regs.

Description: This is a discussion about new product developments, supplementary benefits - Accidental Death, Guaranteed Insurability and automatic inclusion of supplementary benefits rather than optional, product expense trends, considerations in setting commissions for policies with different characteristics, and analyzing and entering new markets.

Description: Even the best algorithms are only effective if they are trained on appropriate data. This article discusses common pitfalls in creating a training data set.